Invoice Annotation with Sparrow/Python
I explain our Streamlit component for invoice/receipt document annotation and labeling. It can be used either to create new annotations or review and edit existing ones. With this component you can add new annotations directly on top of the document image. Existing annotations can be resized/moved and values/labels assigned.
This component is part of Sparrow - our open-source solution for data extraction from invoices/receipts with ML.
Streamlit - Labeling Component:
github.com/katanaml/streamlit...
Sparrow - Data extraction from documents with ML:
github.com/katanaml/sparrow
0:00 Introduction
0:54 GitHub repo
2:45 Demo
5:37 Code
8:10 Summary
CONNECT:
- Subscribe to this KZread channel
- Twitter: / andrejusb
- LinkedIn: / andrej-baranovskij
- Medium: / andrejusb
#machinelearning #webdevelopment #python
Пікірлер: 10
I have been doing text invoice and other annotations since 2019. I have good knowledge and enough experience in annotation
@00_MD_00
7 ай бұрын
good for you
I LOVE It. Thank you💝
Excelente ...gracias por compartir.
hi thank you so much for this helpful code ,I want to make the canvas big and accept the image size without cropping it
@AndrejBaranovskij
Жыл бұрын
Hey, you can do it. For that, you need to modify the function code, where UI dimensions are calculated.
Good morning Andrej, before starting, I think about where to install everything. Means I want to make the annotation process on my local mashine, and the train- / evaluation process on my gpu server. How can I realize that? Or must I do the hole process on my gpu server? Best Stefan
@AndrejBaranovskij
2 ай бұрын
hey. you can run Sparrow data annotation app locally and then training on GPU machine.
Can i use it for algorithme DONUT please
@AndrejBaranovskij
Жыл бұрын
hey. you should check my latest videos in ML playlist, I explain this topics more. For example: kzread.info/dash/bejne/hYihz6iLhaSaYLw.html